View Categories

Features and Labels in Machine Learning

13 min read

Features and Labels in Machine Learning

In Machine Learning, data is generally divided into two important parts: features and labels. Features provide the input information to the model, while the label or target represents the output that the model is trying to predict.

Easy Definition:

Features = Input

Label / Target = Output

Features → Model → Label #

graph LR A[“📊 Features Input Variables”] B[“🤖 Machine Learning Model”] C[“🎯 Label / Target Output”] A –> B B –> C style A fill:#005cbf,color:#fff,stroke:#333,stroke-width:3px style B fill:#6f42c1,color:#fff,stroke:#333,stroke-width:3px style C fill:#28a745,color:#fff,stroke:#333,stroke-width:4px

1. What Are Features? #

Simple Explanation #

Features are the input variables or characteristics that a Machine Learning model uses to learn patterns and make predictions.

Real-Life Example: House Price Prediction #

🏠 House Price Prediction

Suppose we want to predict the price of a house. We may use:

  • Area of the house
  • Number of bedrooms
  • Number of bathrooms
  • House age
  • Location

These are the features because they provide information to the model.

graph TD A[“🏠 House”] A –> B[“📐 Area”] A –> C[“🛏️ Bedrooms”] A –> D[“🚿 Bathrooms”] A –> E[“📅 Age”] A –> F[“📍 Location”] B –> G[“🤖 ML Model”] C –> G D –> G E –> G F –> G G –> H[“💰 Predicted Price”] style A fill:#6f42c1,color:#fff,stroke:#333,stroke-width:3px style B fill:#005cbf,color:#fff,stroke:#333,stroke-width:3px style C fill:#005cbf,color:#fff,stroke:#333,stroke-width:3px style D fill:#005cbf,color:#fff,stroke:#333,stroke-width:3px style E fill:#005cbf,color:#fff,stroke:#333,stroke-width:3px style F fill:#005cbf,color:#fff,stroke:#333,stroke-width:3px style G fill:#ff9800,color:#fff,stroke:#333,stroke-width:3px style H fill:#28a745,color:#fff,stroke:#333,stroke-width:4px
Exam Definition: A feature is an input variable or measurable characteristic used by a Machine Learning model to make predictions.
Remember: Feature → Input used by the model

2. Independent Variables #

Simple Explanation #

In supervised Machine Learning, features are often called independent variables. They are represented by variables such as:

X₁, X₂, X₃, … Xₙ

The model uses these variables to predict the dependent variable.

📌 Example: Student Placement
Feature Example Value
CGPA 8.5
Study Hours 6 hours
Internship Yes
Projects 3

These variables are inputs to the model and can be treated as independent variables.

Exam Definition: Independent variables are input variables used to explain or predict the dependent variable.
Easy Trick: Independent Variable = Input

3. What Is a Label? #

Simple Explanation #

A label is the known output associated with a training example in supervised Machine Learning. It is the value that the model learns to predict.

Example: Spam Detection #

📧 Email Spam Detection

Suppose our model receives information about emails. The features might include:

  • Number of links
  • Number of words
  • Presence of suspicious words
  • Sender information

The label can be:

  • Spam
  • Not Spam
graph LR A[“📧 Email Features”] B[“🤖 ML Model”] C[“🏷️ Label”] A –> B B –> C C –> D[“Spam / Not Spam”] style A fill:#005cbf,color:#fff,stroke:#333,stroke-width:3px style B fill:#6f42c1,color:#fff,stroke:#333,stroke-width:3px style C fill:#ff9800,color:#fff,stroke:#333,stroke-width:3px style D fill:#28a745,color:#fff,stroke:#333,stroke-width:4px
Exam Definition: A label is the known output or target value associated with a training sample in supervised Machine Learning.
Remember: Label → What the model should predict

4. Dependent Variable #

Simple Explanation #

The dependent variable is the output that depends on the input features. In Machine Learning, the dependent variable is commonly called the:

  • Target
  • Label
  • Output variable
🏠 House Price Example

Suppose:

Area = 1500 sq ft

Bedrooms = 3

Age = 5 years

The model predicts:

House Price = ₹60 lakh

Here, house price is the dependent variable because it is the output we want to predict.

Exam Definition: The dependent variable is the output variable whose value is predicted or explained using one or more independent variables.
Easy Trick: Dependent Variable = Output / Target

5. Feature Matrix X #

Simple Explanation #

In Machine Learning, the collection of input features is commonly represented by the capital letter:

X

When there are multiple samples and multiple features, X is called the feature matrix.

📊 Example Dataset
CGPA Study Hours Projects Placement
8.5 6 3 Yes
7.2 4 2 No
9.1 7 4 Yes

The feature matrix X contains:

  • CGPA
  • Study Hours
  • Projects

The Placement column is the target.

Feature Matrix Representation #

X = [
    [8.5, 6, 3],
    [7.2, 4, 2],
    [9.1, 7, 4]
]

Here:

  • Rows → Samples
  • Columns → Features
graph TD A[“Feature Matrix X”] A –> B[“Rows”] A –> C[“Columns”] B –> D[“Samples”] C –> E[“Features”] style A fill:#6f42c1,color:#fff,stroke:#333,stroke-width:3px style B fill:#005cbf,color:#fff,stroke:#333,stroke-width:3px style C fill:#005cbf,color:#fff,stroke:#333,stroke-width:3px style D fill:#28a745,color:#fff,stroke:#333,stroke-width:3px style E fill:#28a745,color:#fff,stroke:#333,stroke-width:3px
Exam Definition: The feature matrix X is a matrix containing the input features for all samples in a Machine Learning dataset.
Remember: X = Features / Inputs

6. Target Vector y #

Simple Explanation #

The target or label values are commonly represented using lowercase:

y

For a supervised Machine Learning problem, y contains the output values that the model is trying to predict. 

y = [
    "Yes",
    "No",
    "Yes"
]

In this example:

  • X = student features
  • y = placement labels
graph LR A[“X Feature Matrix”] B[“🤖 ML Model”] C[“y Target Vector”] A –> B B –> C style A fill:#005cbf,color:#fff,stroke:#333,stroke-width:3px style B fill:#6f42c1,color:#fff,stroke:#333,stroke-width:3px style C fill:#28a745,color:#fff,stroke:#333,stroke-width:4px
Exam Definition: The target vector y contains the target or output values corresponding to the samples in the feature matrix X.
Remember: y = Target / Label / Output

7. Understanding X and y Together #

Suppose we have the following dataset:

CGPA Study Hours Projects Placement
8.5 6 3 Yes
7.2 4 2 No
9.1 7 4 Yes

Then: 

X = [
    [8.5, 6, 3],
    [7.2, 4, 2],
    [9.1, 7, 4]
]

y = [
    "Yes",
    "No",
    "Yes"
]
graph LR A[“X Feature Matrix”] A –> B[“CGPA”] A –> C[“Study Hours”] A –> D[“Projects”] E[“y Target Vector”] E –> F[“Yes”] E –> G[“No”] E –> H[“Yes”] style A fill:#005cbf,color:#fff,stroke:#333,stroke-width:3px style B fill:#005cbf,color:#fff,stroke:#333,stroke-width:2px style C fill:#005cbf,color:#fff,stroke:#333,stroke-width:2px style D fill:#005cbf,color:#fff,stroke:#333,stroke-width:2px style E fill:#28a745,color:#fff,stroke:#333,stroke-width:4px style F fill:#28a745,color:#fff,stroke:#333,stroke-width:2px style G fill:#28a745,color:#fff,stroke:#333,stroke-width:2px style H fill:#28a745,color:#fff,stroke:#333,stroke-width:2px
Most Important Formula:

X → Input Features

y → Target / Output

Model learns the relationship:

X → y

8. Independent Variable vs Dependent Variable #

Concept Meaning Machine Learning Term Symbol
Independent Variable Input used to make a prediction Feature X
Dependent Variable Output being predicted Target / Label y
Exam Shortcut:

Independent Variable → Feature → X

Dependent Variable → Target/Label → y

9. Classification Example #

Email Spam Detection #

Number of Words Number of Links Suspicious Words Label
100 5 Yes Spam
50 1 No Not Spam
120 8 Yes Spam

Here:

X = Number of Words, Number of Links, Suspicious Words

y = Spam / Not Spam

For classification problems, the target y usually represents a category or class. Examples: Spam / Not Spam, Cat / Dog, Yes / No.

10. Regression Example #

House Price Prediction #

For regression, the target is generally a numerical value.

Area Bedrooms Age Price
1200 2 5 ₹40 lakh
1800 3 3 ₹65 lakh
2500 4 2 ₹90 lakh

Here:

X = Area, Bedrooms, Age

y = Price

In regression, the target y is generally a continuous numerical value such as price, salary, temperature, or house area.

11. Complete Feature → Label Workflow #

graph TD A[“📊 Dataset”] A –> B[“X = Features”] A –> C[“y = Label / Target”] B –> D[“🤖 Machine Learning Model”] C –> D D –> E[“🧠 Learn Relationship X → y”] E –> F[“📥 New Input X”] F –> G[“🔮 Prediction ŷ”] style A fill:#6f42c1,color:#fff,stroke:#333,stroke-width:3px style B fill:#005cbf,color:#fff,stroke:#333,stroke-width:3px style C fill:#28a745,color:#fff,stroke:#333,stroke-width:4px style D fill:#ff9800,color:#fff,stroke:#333,stroke-width:3px style E fill:#6f42c1,color:#fff,stroke:#333,stroke-width:3px style F fill:#005cbf,color:#fff,stroke:#333,stroke-width:3px style G fill:#28a745,color:#fff,stroke:#333,stroke-width:4px

During training, the model receives both X and the corresponding y values in supervised learning. It learns a relationship between them. Later, when a new X is provided, the model produces a predicted output, commonly written as:

ŷ (y-hat)

Important Symbols:

X → Features / Inputs

y → Actual Target / Label

ŷ → Predicted Target

12. Quick Revision for Exams #

Features: Input variables used by the model.

Independent Variables: Variables used as inputs to predict the output.

Label: Known output associated with a training sample.

Dependent Variable: Output variable being predicted.

Feature Matrix X: Matrix containing input features for multiple samples.

Target Vector y: Vector containing the corresponding target values.

Prediction ŷ: Output predicted by the trained model.

13. One Diagram to Remember Everything #

graph LR A[“📥 Input Data”] B[“X Feature Matrix”] C[“🤖 ML Model”] D[“y Actual Target”] E[“ŷ Predicted Target”] A –> B B –> C D –> C C –> E B -. “Independent Variables” .-> C D -. “Dependent Variable” .-> C style A fill:#6f42c1,color:#fff,stroke:#333,stroke-width:3px style B fill:#005cbf,color:#fff,stroke:#333,stroke-width:4px style C fill:#ff9800,color:#fff,stroke:#333,stroke-width:3px style D fill:#28a745,color:#fff,stroke:#333,stroke-width:4px style E fill:#e91e63,color:#fff,stroke:#333,stroke-width:4px

Conclusion #

Features and labels are fundamental concepts in supervised Machine Learning. The easiest way to remember them is:

Features = Input = Independent Variables = X

Label = Target = Dependent Variable = y

Prediction = ŷ

The model learns the relationship between X and y during training and then uses new feature values X to generate predictions ŷ.

Features and Labels in Machine Learning Quiz #

1. What is a feature in Machine Learning?



  • The final prediction made by a model


  • An input variable used by the model


  • The error of the model


  • The name of the algorithm

2. What is another common name for a feature?



  • Dependent variable


  • Target variable


  • Independent variable


  • Prediction variable

3. In Machine Learning, what does the target or label represent?



  • Input data


  • Output that the model is trying to predict


  • Number of features


  • Training algorithm

4. Which symbol is commonly used to represent the feature matrix?



  • y


  • z


  • X


  • T

5. If a dataset has 1,000 samples and 5 features, what is the typical shape of the feature matrix X?



  • (5, 1,000)


  • (1,000, 5)


  • (1,005)


  • (5, 5)

6. If X represents the features and y represents the actual target values, what does a trained model generally produce for a new X?



  • Another feature matrix only


  • A predicted target value ŷ


  • A new training dataset


  • A hyperparameter

7. In a feature matrix X, what do the columns generally represent?



  • Samples


  • Predictions


  • Features


  • Labels only

8. In a house price prediction problem, which of the following can be a feature?



  • House price


  • Prediction error


  • Number of bedrooms


  • Model accuracy

9. In a house price prediction problem, what is the dependent variable if the goal is to predict the house price?



  • Number of bedrooms


  • House area


  • House price


  • Location

10. Which statement correctly describes the relationship between X and y in supervised learning?



  • X contains targets and y contains features


  • X contains features and y contains target values


  • Both X and y contain only features


  • Both X and y contain model parameters

11. What is the dependent variable also commonly called in Machine Learning?



  • Feature


  • Independent variable


  • Target or label


  • Hyperparameter

12. Suppose X contains student CGPA, study hours, and number of projects, while y contains Placement = Yes/No. What does y represent?



  • Feature matrix


  • Independent variables


  • Target vector


  • Hyperparameters

13. What does y-hat (ŷ) generally represent in Machine Learning?



  • Actual target value


  • Feature matrix


  • Predicted target value


  • Training dataset

14. In a spam detection system, which of the following is most likely to be a label?



  • Number of words in an email


  • Number of links


  • Spam or Not Spam


  • Email length

15. In a regression problem, which of the following can be a target variable y?



  • Number of bedrooms


  • House area


  • House price


  • Location

Updated on September 23, 2026

What are your Feelings

  • Happy
  • Normal
  • Sad

Powered by BetterDocs

Scroll to Top